strategy
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection via the natural language strategy descriptions.
- Ingestion points: User-provided strategy descriptions and command arguments in the
/strategy createand/strategy from-templatecommands. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands were found in the command parsing or strategy definition logic.
- Capability inventory: The skill possesses the capability to execute financial trades (via the 'polymarket' and 'kalshi' platforms) and allocate portfolio capital.
- Sanitization: The input is passed directly to the strategy builder without visible sanitization or filtering of adversarial natural language instructions.
Audit Metadata